Department of Diagnostic and Interventional Radiology, Eberhard-Karls University, Hoppe-Seyler-Str. 3, 72076 Tuebingen, Germany (A.S.B., R.D., B.S., J.M., P.G., G.G., S.A., C.A.).
Department of Diagnostic and Interventional Radiology, Eberhard-Karls University, Hoppe-Seyler-Str. 3, 72076 Tuebingen, Germany (A.S.B., R.D., B.S., J.M., P.G., G.G., S.A., C.A.).
Acad Radiol. 2024 May;31(5):2144-2155. doi: 10.1016/j.acra.2023.11.003. Epub 2023 Nov 21.
In interventional bronchial artery embolization (BAE), periprocedural cone beam CT (CBCT) improves guiding and localization. However, a trade-off exists between 6-second runs (high radiation dose and motion artifacts, but low noise) and 3-second runs (vice versa). This study aimed to determine the efficacy of an advanced deep learning denoising (DLD) technique in mitigating the trade-offs related to radiation dose and image quality during interventional BAE CBCT.
This study included BMI-matched patients undergoing 6-second and 3-second BAE CBCT scans. The dose-area product values (DAP) were obtained. All datasets were reconstructed using standard weighted filtered back projection (OR) and a novel DLD software. Objective image metrics were derived from place-consistent regions of interest, including CT numbers of the Aorta and lung, noise, and contrast-to-noise ratio. Three blinded radiologists performed subjective assessments regarding image quality, sharpness, contrast, and motion artifacts on all dataset combinations in a forced-choice setup (-1 = inferior, 0 = equal; 1 = superior). The points were averaged per item for a total score. Statistical analysis ensued using a properly corrected mixed-effects model with post hoc pairwise comparisons.
Sixty patients were assessed in 30 matched pairs (age 64 ± 15 years; 10 female). The mean DAP for the 6 s and 3 s runs was 2199 ± 185 µGym² and 1227 ± 90 µGym², respectively. Neither low-dose imaging nor the reconstruction method introduced a significant HU shift (p ≥ 0.127). The 3 s-DLD presented the least noise and superior contrast-to-noise ratio (CNR) (p < 0.001). While subjective evaluation revealed no noticeable distinction between 6 s-DLD and 3 s-DLD in terms of quality (p ≥ 0.996), both outperformed the OR variants (p < 0.001). The 3 s datasets exhibited fewer motion artifacts than the 6 s datasets (p < 0.001).
DLD effectively mitigates the trade-off between radiation dose, image noise, and motion artifact burden in regular reconstructed BAE CBCT by enabling diagnostic scans with low radiation exposure and inherently low motion artifact burden at short examination times.
在介入性支气管动脉栓塞（BAE）中，术中超快速锥形束 CT（CBCT）可提高引导和定位的准确性。然而，6 秒扫描（高辐射剂量和运动伪影，但噪声低）与 3 秒扫描（反之亦然）之间存在权衡。本研究旨在确定一种先进的深度学习降噪（DLD）技术在减轻介入性 BAE CBCT 中与辐射剂量和图像质量相关的权衡方面的疗效。
本研究纳入了接受 6 秒和 3 秒 BAE CBCT 扫描的 BMI 匹配患者。获得剂量面积乘积值（DAP）。所有数据集均使用标准加权滤波反投影（OR）和新的 DLD 软件进行重建。从一致的 ROI 中获得客观的图像指标，包括主动脉和肺部的 CT 值、噪声和对比噪声比。三位盲法放射科医生在强制选择设置下对所有数据集组合的图像质量、锐度、对比度和运动伪影进行主观评估（-1=差，0=相等；1=优）。每个项目的分数进行平均得到总分。采用适当校正的混合效应模型进行统计分析，并进行事后两两比较。
对 30 对匹配患者（年龄 64±15 岁；10 名女性）进行了 60 例评估。6 秒和 3 秒运行的平均 DAP 分别为 2199±185 µGym²和 1227±90 µGym²。低剂量成像或重建方法均未导致明显的 HU 偏移（p≥0.127）。3 秒-DLD 噪声最小，对比噪声比（CNR）最高（p<0.001）。虽然主观评估显示 6 秒-DLD 和 3 秒-DLD 在质量方面没有明显差异（p≥0.996），但两者均优于 OR 变体（p<0.001）。3 秒数据集的运动伪影比 6 秒数据集少（p<0.001）。
DLD 通过在短检查时间内实现低辐射暴露和固有低运动伪影负担的诊断性扫描，有效地减轻了常规重建 BAE CBCT 中辐射剂量、图像噪声和运动伪影负担之间的权衡。
